Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1493 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1637037 (Python Code)

Max Activating Token Index: 296

Text #1

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1390498 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1464120 (Python Code)

Max Activating Token Index: 798

Text #3

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1381633 (Python Code)

Max Activating Token Index: 736

Text #4

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2785. Min Act: -0.0000

Data Index: 854104 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1455581 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1370777 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1373049 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1557811 (Python Code)

Max Activating Token Index: 546

Text #9

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1372092 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1402784 (Python Code)

Max Activating Token Index: 206

Text #11

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2365. Min Act: -0.0000

Data Index: 1454094 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1524928 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1381556 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1516052 (Python Code)

Max Activating Token Index: 679

Text #15

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2501. Min Act: -0.0000

Data Index: 773412 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1435633 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1463043 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1573344 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1528969 (Python Code)

Max Activating Token Index: 534